# Attract or Distract: Exploit the Margin of Open Set

arXiv: https://arxiv.org/abs/1908.01925 · HTML: https://mlsanity.com/paper/1908.01925/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://mlsanity.com/paper/2107.02067/) (2021)
- [Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering](https://mlsanity.com/paper/2103.04580/) (2021)
- [Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar](https://mlsanity.com/paper/2103.08863/) (2021)
- [Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation](https://mlsanity.com/paper/2207.09280/) (2022)
- [OneRing: A Simple Method for Source-free Open-partial Domain Adaptation](https://mlsanity.com/paper/2206.03600/) (2022)
- [IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.12947/) (2022)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2106.06237/) (2021)
- [Contrastive Learning for Cross-Domain Open World Recognition](https://mlsanity.com/paper/2203.09257/) (2022)
- [Provably Uncertainty-Guided Universal Domain Adaptation](https://mlsanity.com/paper/2209.09616/) (2022)
- [Incremental Open-set Domain Adaptation](https://mlsanity.com/paper/2409.00530/) (2024)

## Abstract (arXiv)

Open set domain adaptation aims to diminish the domain shift across domains, with partially shared classes. There exist unknown target samples out of the knowledge of source domain. Compared to the close set setting, how to separate the unknown (unshared) class from the known (shared) ones plays a key role. Whereas, previous methods did not emphasize the semantic structure of the open set data, which may introduce bias into the domain alignment and confuse the classifier around the decision boundary. In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source. 2)Semantic Contrastive Mapping, which aims to push the unknown class away from the decision boundary. Empirically, we demonstrate that our method performs favourably against the state-of-the-art methods on representative benchmarks, e.g. Digit datasets and Office-31 datasets.